Manipulation planning on constraint manifolds

By Dmitry Berenson, Siddhartha S. Srinivasa, D. Ferguson, James J. Kuffner Jr.. 2009

359 citations recorded by the source corpus.

We present the Constrained Bi-directional Rapidly-Exploring Random Tree (CBiRRT) algorithm for planning paths in configuration spaces with multiple constraints. This algorithm provides a general framework for handling a variety of constraints in manipulation planning including torque limits, constraints on the pose of an object held by a robot, and constraints for following workspace surfaces. CBiRRT extends the Bi-directional RRT (BiRRT) algorithm by using projection techniques to explore the configuration space manifolds that correspond to constraints and to find bridges between them. Consequently, CBiRRT can solve many problems that the BiRRT cannot, and only requires one additional parameter: the allowable error for meeting a constraint. We demonstrate the CBiRRT on a 7DOF WAM arm with a 4DOF Barrett hand on a mobile base. The planner allows this robot to perform household tasks, solve puzzles, and lift heavy objects.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Robotics & Control

Citations in the corpus

A Planning Framework for Non-Prehensile Manipulation under Clutter and Uncertainty (2012, positive): “To implement this action we use an extension of the Rapidly-Exploring Random Tree (RRT) (Lavalle and Kuffner 2000) planner, namely the Constrained Bi-directional RRT planner (CBiRRT) (Berenson et al 2009a).”
A Survey of Preference-Based Reinforcement Learning Methods (2017, methodology): “The use of sampling-based rapidly-exploring random trees (RRT; LaValle and Kuffner 1999) and their constrained bi-directional variant (CBiRRT; Berenson et al. 2009) was explored in (Jain et al.”
The YCB object and Model set: Towards common benchmarks for manipulation research (2015, methodology): “In other cases such as CBiRRT [31] compute collisions directly using an optimized mesh collision checker.”
STOMP: Stochastic trajectory optimization for motion planning (2011, methodology): “They have been used to address task space constraints and to impose torque constraints while lifting heavy objects [6].”
Integrated Task and Motion Planning (2020, methodology): “Several approaches have provided probabilistically complete methods for constrained motion planning using projection (31, 32) and atlas-based techniques (33, 34, 35).”
End-to-end dexterous manipulation with deliberate interactive estimation (2012, methodology): “Variations of the Rapidly-Exploring Random Tree (RRT) technique [24] are commonly used to find a collision-”
Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols (2015, methodology): “Once grasped, the robot lifted the pitcher and planned a pouring motion using the CBiRRT planner with TSR constraints to rotate the pitcher about a fixed point in front of the spout.”
HERB: a home exploring robotic butler (2010, methodology): “To create plans for such constrained tasks, we have developed the Constrained BiDirectional Rapidly-exploring Random Tree (CBiRRT) (Berenson et al. 2009b) motion planning algorithm, which uses Jacobian-based projection methods as well as efficient constraint-checking to explore constraint manifolds…”